Big Text Visual Analytics in Sensemaking

Learning from text data often involves a loop of tasks that iterate between foraging for information and synthesizing it in incremental hypotheses. Past research has shown the advantages of using spatial workspaces as a means for synthesizing information through externalizing hypotheses and creating spatial schemas. However, spatializing the entirety of datasets becomes prohibitive as the number of documents available to the analysts grows, particularly when only a small subset are relevant to the tasks at hand. To address this issue, we applied the multi-model semantic interaction (MSI) technique, which leverages user interactions to aid in the display layout (as was seen in previous semantic interaction work), forage for new, relevant documents as implied by the interactions, and place them in context of the user's existing spatial layout. Thus, this approach cleanly embeds visual analytics of big text collections directly into the human sensemaking process.